Search Results for author:
Found 14 papers, 4 papers with code
Diversity and Diffusion: Observations on Synthetic Image Distributions with Stable Diffusion
Recent progress in text-to-image (TTI) systems, such as StableDiffusion, Imagen, and DALL-E 2, have made it possible to create realistic images with simple text prompts.
Texture for Colors: Natural Representations of Colors Using Variable Bit-Depth Textures
We present an automated method to transform an image to a set of binary textures that represent not only the intensities, but also the colors of the original.
Table-Based Neural Units: Fully Quantizing Networks for Multiply-Free Inference
We show results that are within 1. 6% of the reported, non-quantized performance on MobileNet using only 40 entries in our table.
Neural Image Decompression: Learning to Render Better Image Previews
A rapidly increasing portion of Internet traffic is dominated by requests from mobile devices with limited- and metered-bandwidth constraints.
No Multiplication? No Floating Point? No Problem! Training Networks for Efficient Inference
For successful deployment of deep neural networks on highly--resource-constrained devices (hearing aids, earbuds, wearables), we must simplify the types of operations and the memory/power resources used during inference.
Representing Images in 200 Bytes: Compression via Triangulation
A rapidly increasing portion of internet traffic is dominated by requests from mobile devices with limited and metered bandwidth constraints.
Empirical Explorations in Training Networks with Discrete Activations
Surprisingly, we find that despite reducing the number of values that can be represented in the output activations from $2^{32}-2^{64}$ to between 64 and 256, there is little to no degradation in network performance across a variety of different settings.
Hiding Images in Plain Sight: Deep Steganography
Steganography is the practice of concealing a secret message within another, ordinary, message.
Adversarial Transformation Networks: Learning to Generate Adversarial Examples
We efficiently train feed-forward neural networks in a self-supervised manner to generate adversarial examples against a target network or set of networks.
Deep Learning for Explicitly Modeling Optimization Landscapes
To represent the search space concisely and accurately, the deep networks must encode information about the underlying parameter interactions and their contributions to the quality of the solution.
Traffic Lights with Auction-Based Controllers: Algorithms and Real-World Data
Real-time optimization of traffic flow addresses important practical problems: reducing a driver's wasted time, improving city-wide efficiency, reducing gas emissions and improving air quality.
Learning Typographic Style
Typography is a ubiquitous art form that affects our understanding, perception, and trust in what we read.
Labeling the Features Not the Samples: Efficient Video Classification with Minimal Supervision
Our method works both as a feature selection mechanism and as a fully competitive classifier.
Variable Rate Image Compression with Recurrent Neural Networks
A large fraction of Internet traffic is now driven by requests from mobile devices with relatively small screens and often stringent bandwidth requirements.
